Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Diagram Question Answering on AI2D (test)

94.7Accuracy

Claude 3.5

72.13277.99183.8589.709Jun 24, 2024Oct 5, 2024Jan 16, 2025Apr 29, 2025Aug 10, 2025Nov 21, 2025Mar 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2024.07
94.7
94.7
2024.07
94.4
94.4
94.4
2024.07
94.2
2024.12
94.2
2024.12
94.2
2024.12
94.2
2024.07
94.1
2024.12
94.1
2025.06
93.9
2024.07
93
2025.06
93
2024.12
92.3
2024.12
92.3
2024.12
92
2024.12
91.9
2025.06
91.8
2024.12
91
2025.06
90
2025.06
89.1
2024.12
88.9
2024.12
87.1
2024.12
85.6
2026.03
85
2025.06
84.8
84.8
2026.03
84.8
2026.03
84.7
2024.09
84.6
84.6
2024.07
84.4
2025.12
83.9
2024.12
83.8
2024.12
83.8
2024.12
83.8
2025.06
83.8
2024.12
83
2024.12
83
2024.12
83
2026.01
83
2026.03
83
2025.06
82.9
2026.03
82.7
2025.12
82.2
2026.01
82.2
2025.06
82.1
2024.12
81.6
2025.12
81.6
2024.12
81.5
2024.12
81.4
2024.12
81.4
2024.12
81.4
2025.12
81.4
2025.06
81.4
2025.06
81.4
80.4
2024.12
79.9
2024.09
79.7
2024.12
79.7
2024.09
79.1
2024.12
79
2025.06
78.9
2024.12
78.7
2024.12
78.5
2025.12
78.4
2025.06
78.4
2024.07
78.2
2024.12
78.2
2026.01
77.9
2025.12
77.8
2025.06
77.8
2026.01
77.6
2026.01
77.5
2025.06
77.5
2024.09
77.2
2024.09
76.7
2024.12
76.6
2024.12
76.3
2025.06
76.1
2026.01
76
2024.09
75.9
2025.06
75
2025.06
74.9
2024.12
74.7
2025.12
74.4
2024.12
74.2
2024.09
74.1
2024.12
74.1
2025.06
74.1
2025.06
74
2024.12
73.6
2025.06
73.6
73.5
2025.06
73.4
2024.09
73.3
2024.06
73.1
2024.12
73
2025.12
73
Showing 100 of 142 rows